Imported Upstream version 2014.08.05

[youtubedl] / youtube_dl / extractor / escapist.py

diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py
index 86b145bca9d9da95024525be3f4b5cf441b36b58..272dfe1f643208a31635dade0e561c8eb009aab7 100644 (file)
--- a/youtube_dl/extractor/escapist.py
+++ b/youtube_dl/extractor/escapist.py
@@ -1,9 +1,9 @@
-import json
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
 
     ExtractorError,
@@ -11,58 +11,72 @@ from ..utils import (
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
+    _TEST = {
+        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'info_dict': {
+            'id': '6618',
+            'ext': 'mp4',
+            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+            'uploader': 'the-escapist-presents',
+            'title': "Breaking Down Baldur's Gate",
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         showName = mobj.group('showname')
-        videoId = mobj.group('episode')
-
-        self.report_extraction(videoId)
-        webpage = self._download_webpage(url, videoId)
+        video_id = mobj.group('id')
 
-        videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
-            webpage, u'description', fatal=False)
+        self.report_extraction(video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
-            webpage, u'thumbnail', fatal=False)
+        videoDesc = self._html_search_regex(
+            r'<meta name="description" content="([^"]*)"',
+            webpage, 'description', fatal=False)
 
-        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
-            webpage, u'player url')
+        playerUrl = self._og_search_video_url(webpage, name=u'player URL')
 
-        title = self._html_search_regex('<meta name="title" content="([^"]*)"',
-            webpage, u'player url').split(' : ')[-1]
+        title = self._html_search_regex(
+            r'<meta name="title" content="([^"]*)"',
+            webpage, 'title').split(' : ')[-1]
 
-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
+        configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
         configUrl = compat_urllib_parse.unquote(configUrl)
 
-        configJSON = self._download_webpage(configUrl, videoId,
-                                            u'Downloading configuration',
-                                            u'unable to download configuration')
-
-        # Technically, it's JavaScript, not JSON
-        configJSON = configJSON.replace("'", '"')
-
+        formats = []
+
+        def _add_format(name, cfgurl, quality):
+            config = self._download_json(
+                cfgurl, video_id,
+                'Downloading ' + name + ' configuration',
+                'Unable to download ' + name + ' configuration',
+                transform_source=lambda s: s.replace("'", '"'))
+
+            playlist = config['playlist']
+            formats.append({
+                'url': playlist[1]['url'],
+                'format_id': name,
+                'quality': quality,
+            })
+
+        _add_format('normal', configUrl, quality=0)
+        hq_url = (configUrl +
+                  ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
         try:
-            config = json.loads(configJSON)
-        except (ValueError,) as err:
-            raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+            _add_format('hq', hq_url, quality=1)
+        except ExtractorError:
+            pass  # That's fine, we'll just use normal quality
 
-        playlist = config['playlist']
-        videoUrl = playlist[1]['url']
+        self._sort_formats(formats)
 
-        info = {
-            'id': videoId,
-            'url': videoUrl,
+        return {
+            'id': video_id,
+            'formats': formats,
             'uploader': showName,
-            'upload_date': None,
             'title': title,
-            'ext': 'mp4',
-            'thumbnail': imgUrl,
+            'thumbnail': self._og_search_thumbnail(webpage),
             'description': videoDesc,
             'player_url': playerUrl,
         }
-
-        return [info]